Find answers from the community

Home
Members
barlazy
b
barlazy
Offline, last seen 2 days ago
Joined September 29, 2024
@Logan M is there a private adaptation of llamaindex in Go that you know of which you would recommend?
2 comments
L
b
Hi @Logan M! Is there an easy way to control the ReAct Agent's SYS prompt?
8 comments
L
b
b
barlazy
·

Header

@Logan M some gov websites require you to pass a user agent in the header, is there a way to customize that request on LlamaParse to retrieve that information?
1 comment
L
@Logan M Can we cache the loading of the PDF? https://docs.llamaindex.ai/en/stable/examples/cookbooks/oreilly_course_cookbooks/Module-8/Advanced_RAG_with_LlamaParse/

Every new run it seems to start parsing the file--
Plain Text
Started parsing the file under job_id d2f528c8-7756-4b7a-53d3a771
5it [00:00, 49461.13it/s]
2it [00:00, 41734.37it/s]
0it [00:00, ?it/s]
4it [00:00, 58254.22it/s]
0it [00:00, ?it/s]
0it [00:00, ?it/s]
0it [00:00, ?it/s]
0it [00:00, ?it/s]
1it [00:00, 19878.22it/s]
1it [00:00, 11491.24it/s]
4it [00:00, 62368.83it/s]
30it [00:00, 528693.78it/s]
9 comments
L
b
Hey @Logan M , just curious if I could use OpenAI's in-built structured-output feature usint the OpenAI llm? Didn't look into the llama_index source yet, so thought I'd ask here.
1 comment
L
Hi @Logan M , what would be the easiest way to infer the fn_schema to pass in a Function Tool?

Context: The function tool is hosted elsewhere and the schema varies per use-case. At inference, I want to be able to send a string that can be used as the fn_schema. My question will then be, what should be the structure and the contents of this string and how to parse it into a llama index compatible fn_schema?
4 comments
L
b
In stepwise execution, once a tool call has finished, can I modify the tool response externally before the next step, ensuring that the modified response goes into the next step?
4 comments
b
L
Trying to run the OpenAI agent stepwise, but it calls the tool twice in the same step, would love some help @Logan M

Plain Text
> Running step f2581fdf-b673-4d9e-8b46-5b4d731071b2. Step input: What is `(15746 * 17364) + 23123`?
Added user message to memory: What is `(15746 * 17364) + 23123`?
=== Calling Function ===
Calling function: multiply with args: {"a": 15746, "b": 17364}
Got output: 273413544
========================

=== Calling Function ===
Calling function: add with args: {"a": 23123, "b": 0}
Got output: 23123
========================
7 comments
L
b